JunnYu / FLASHQuad_pytorch
FLASHQuad_pytorch
☆66Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for FLASHQuad_pytorch
- R-Drop方法在中文任务上的简单实验☆90Updated 2 years ago
- 基于Gated Attention Unit的Transformer模型(尝鲜版)☆97Updated last year
- Apply the Circular to the Pretraining Model☆38Updated 2 years ago
- RoFormer升级版☆149Updated 2 years ago
- 记录NLP、CV、搜索、推荐等AI岗位最新情况。☆28Updated last year
- Open source code for Paper "A Co-Interactive Transformer for Joint Slot Filling and Intent Detection"☆75Updated 2 years ago
- ☆53Updated 2 years ago
- pytorch版simcse无监督语义相似模型☆22Updated 3 years ago
- Chinese Machine Reading 2021海华AI挑战赛·中文阅读理解·技术组·第三名☆21Updated 3 years ago
- Open source code for EMNLP 2020 Findings Paper "AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slo…☆82Updated 2 years ago
- ☆34Updated 3 years ago
- ☆34Updated 2 years ago
- 中文bigbird预训练模型☆89Updated 2 years ago
- Pretrain CPM-1☆51Updated 3 years ago
- pytorch版unilm模型☆25Updated 3 years ago
- WoBERT_pytorch☆40Updated 3 years ago
- This repository implements a prompt tuning model for hierarchical text classification. This work has been accepted as the long paper "HPT…☆62Updated last year
- A concise implementation of SimCSE☆17Updated 3 years ago
- 实现了Transformer中的几种位置编码方案☆38Updated 3 years ago
- CTC2021-中文文本纠错大赛的SOTA方案及在线演示☆72Updated last year
- Label Mask for Multi-label Classification☆55Updated 3 years ago
- Pattern-Exploiting Training在中文上的简单实验☆170Updated 4 years ago
- 句子匹配模型,包括无监督的SimCSE、ESimCSE、PromptBERT,和有监督的SBERT、CoSENT。☆97Updated 2 years ago
- Data Augmentation with a Generation Approach for Low-resource Tagging Tasks☆79Updated 3 years ago
- P-tuning方法在中文上的简单实验☆138Updated 3 years ago
- This is the official code for paper titled "Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Models".☆67Updated 3 years ago
- 2021搜狐校园文本匹配算法大赛baseline☆45Updated 3 years ago
- 擂台赛3-大规模预训练调优比赛的示例代码与baseline实现☆38Updated 2 years ago
- Python下shuffle几百G文件☆33Updated 3 years ago
- GAIIC2022商品标题实体识别Baseline,使用GlobalPointer实现,线上0.80349☆52Updated 2 years ago